C-RNN-GAN: Continuous recurrent neural networks with adversarial training

Abstract

Generative adversarial networks have been proposed as a way of efficiently training deep generative neural networks. We propose a generative adversarial model that works on continuous sequential data, and apply it by training it on a collection of classical music. We conclude that it generates music that sounds better and better as the model is trained, report statistics on generated music, and let the reader judge the quality by downloading the generated songs.

Accepted to Constructive Machine Learning Workshop (CML) at NIPS 2016 in Barcelona, Spain, December 10

References in corpus (1)

• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

Cited by in corpus (41)

• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Probabilistic Forecasting of Sensory Data with Generative Adversarial Networks - ForGAN
• A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
• Conditional GAN for timeseries generation
• Wasserstein Learning of Deep Generative Point Process Models
• Generative adversarial networks in time series: A survey and taxonomy
• Collecting the Public Perception of AI and Robot Rights
• MusPy: A Toolkit for Symbolic Music Generation
• PIANOTREE VAE: Structured Representation Learning for Polyphonic Music
• eCommerceGAN : A Generative Adversarial Network for E-commerce
• Adversarial Network Bottleneck Features for Noise Robust Speaker Verification
• Causal Inference for Time series Analysis: Problems, Methods and Evaluation
• Future Frame Prediction Using Convolutional VRNN for Anomaly Detection
• Interaction-aware Multi-agent Tracking and Probabilistic Behavior Prediction via Adversarial Learning
• TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
• Explicitly Conditioned Melody Generation: A Case Study with Interdependent RNNs
• Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders
• Hide-and-Seek Privacy Challenge
• Generating Music with a Self-Correcting Non-Chronological Autoregressive Model
• Can GAN originate new electronic dance music genres? -- Generating novel rhythm patterns using GAN with Genre Ambiguity Loss
• A Survey on Audio Synthesis and Audio-Visual Multimodal Processing
• Data Augmentation for Enhancing EEG-based Emotion Recognition with Deep Generative Models
• A Novel CNet-assisted Evolutionary Level Repairer and Its Applications to Super Mario Bros
• BasketballGAN: Generating Basketball Play Simulation Through Sketching
• Predicting Confusion from Eye-Tracking Data with Recurrent Neural Networks
• Automatic Neural Lyrics and Melody Composition
• Synthesis of pulses from particle detectors with a Generative Adversarial Network (GAN)
• Reinforcement Learning with Policy Mixture Model for Temporal Point Processes Clustering
• Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables
• A Spectral Enabled GAN for Time Series Data Generation
• AnimGAN: A Spatiotemporally-Conditioned Generative Adversarial Network for Character Animation
• Generative Models for Security: Attacks, Defenses, and Opportunities
• Towards Better Adversarial Synthesis of Human Images from Text
• Music Generation using Three-layered LSTM
• MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
• Sinusoidal wave generating network based on adversarial learning and its application: synthesizing frog sounds for data augmentation
• Personality-Driven Gaze Animation with Conditional Generative Adversarial Networks
• RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning
• Recurrent Adversarial Service Times
• STEP-GAN: A Step-by-Step Training for Multi Generator GANs with application to Cyber Security in Power Systems